Interpretable Model Based on Pyramid Scene Parsing Features for Brain Tumor MRI Image Segmentation

被引:3
作者
Zhao, Mingyang [1 ]
Xin, Junchang [2 ,3 ]
Wang, Zhongyang [1 ]
Wang, Xinlei [2 ,4 ]
Wang, Zhiqiong [1 ,5 ]
机构
[1] Northeastern Univ, Coll Med & Biol Informat Engn, Shenyang 110169, Peoples R China
[2] Northeastern Univ, Sch Comp Sci & Engn, Shenyang 110169, Peoples R China
[3] Northeastern Univ, Key Lab Big Data Management & Analyt Liaoning Pro, Shenyang 110169, Peoples R China
[4] Neusoft Corp Ltd, Inst Intelligent Healthcare Technol, Shenyang 110179, Peoples R China
[5] Harbin Engn Univ, Acoust Sci & Technol Lab, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1155/2022/8000781
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Due to the black box model nature of convolutional neural networks, computer-aided diagnosis methods based on depth learning are usually poorly interpretable. Therefore, the diagnosis results obtained by these unexplained methods are difficult to gain the trust of patients and doctors, which limits their application in the medical field. To solve this problem, an interpretable depth learning image segmentation framework is proposed in this paper for processing brain tumor magnetic resonance images. A gradient-based class activation mapping method is introduced into the segmentation model based on pyramid structure to visually explain it. The pyramid structure constructs global context information with features after multiple pooling layers to improve image segmentation performance. Therefore, class activation mapping is used to visualize the features concerned by each layer of pyramid structure and realize the interpretation of PSPNet. After training and testing the model on the public dataset BraTS2018, several sets of visualization results were obtained. By analyzing these visualization results, the effectiveness of pyramid structure in brain tumor segmentation task is proved, and some improvements are made to the structure of pyramid model based on the shortcomings of the model shown in the visualization results. In summary, the interpretable brain tumor image segmentation method proposed in this paper can well explain the role of pyramid structure in brain tumor image segmentation, which provides a certain idea for the application of interpretable method in brain tumor segmentation and has certain practical value for the evaluation and optimization of brain tumor segmentation model.
引用
收藏
页数:10
相关论文
共 50 条
[1]   AM-PSPNet: Pyramid Scene Parsing Network Based on Attentional Mechanism for Image Semantic Segmentation [J].
Wu, Dikang ;
Zhao, Jiamei ;
Wang, Zhifang .
DATA SCIENCE (ICPCSEE 2022), PT I, 2022, 1628 :425-434
[2]   Multistage Shallow Pyramid Parsing for Road Scene Understanding Based on Semantic Segmentation [J].
Nurhadiyatna, Adi ;
Loncaric, Sven .
PROCEEDINGS OF THE 2019 11TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS (ISPA 2019), 2019, :198-203
[3]   Brain Tumor Image Segmentation in MRI Image [J].
Tjahyaningtijas, Hapsari Peni Agustin .
2ND INTERNATIONAL CONFERENCE ON VOCATIONAL EDUCATION AND ELECTRICAL ENGINEERING (ICVEE), 2018, 336
[4]   A Refined Pyramid Scene Parsing Network for Polarimetric SAR Image Semantic Segmentation in Agricultural Areas [J].
Zhang, Rui ;
Chen, Jie ;
Feng, Liang ;
Li, Shuang ;
Yang, Wei ;
Guo, Ding .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[5]   A terrain segmentation method based on pyramid scene parsing-mobile network for outdoor robots [J].
Zhang, Botao ;
Hong, Tao ;
Xiong, Rong ;
Chepinskiy, Sergey A .
International Journal of Advanced Robotic Systems, 2021, 18 (05)
[6]   A terrain segmentation method based on pyramid scene parsing-mobile network for outdoor robots [J].
Zhang, Botao ;
Hong, Tao ;
Xiong, Rong ;
Chepinskiy, Sergey A. .
INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2021, 18 (05)
[7]   Segmentation of field grape bunches via an improved pyramid scene parsing network [J].
Chen, Shan ;
Song, Yuyang ;
Su, Jinya ;
Fang, Yulin ;
Shen, Lei ;
Mi, Zhiwen ;
Su, Baofeng .
INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING, 2021, 14 (06) :185-194
[8]   MRI brain tumor segmentation based on texture features and kernel sparse coding [J].
Tong, Jijun ;
Zhao, Yingjie ;
Zhang, Peng ;
Chen, Lingyu ;
Jiang, Lurong .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2019, 47 :387-392
[9]   Segmentation and Classification of Brain Tumor using Wavelet and Zernike based features on MRI [J].
Sornam, M. ;
Kavitha, Muthu Subash ;
Shalini, R. .
2016 IEEE INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTER APPLICATIONS (ICACA), 2016, :166-169
[10]   Development of a deep wavelet pyramid scene parsing semantic segmentation network for scene perception in indoor environments [J].
Aslan S.N. ;
Uçar A. ;
Güzeliş C. .
Journal of Ambient Intelligence and Humanized Computing, 2023, 14 (09) :12673-12695